CLI Usage

1. Using CLI for Prediction

CLI (Command-Line Interface) is a way for users to interact with computers or software programs, where users run programs or execute tasks by typing text commands, rather than clicking icons or buttons through a graphical user interface (GUI).

2. CLI Usage Syntax

​x
yolo TASK MODE ARGS
​
Where   TASK (optional) is one of [detect, segment, classify, pose, obb]
        MODE (required) is one of [train, val, predict, export, track, benchmark]
        ARGS (optional) are any number of custom 'arg=value' pairs like 'imgsz=320' that override defaults.

3. Image Prediction

Use yolo26n.pt to predict the built-in images in the ultralytics26 project: If the system cannot find the corresponding model file in the directory where the command is run, it will automatically download (if download fails, you can copy the model in yourself)

Enter the project folder:

xxxxxxxxxx
cd ~/ultralytics/

Use yolo26n.pt to detect images in the target folder and output results:

xxxxxxxxxx
yolo predict model=yolo26n.pt source='assets/bus.jpg'

Effect Preview

yolo recognition output image location: /home/jetson/ultralytics/runs/detect/predict2

Each time it runs, the predict under this folder automatically increments by 1

4. Video Prediction

Use yolo26n.pt to predict videos in the ultralytics project (not built-in ultralytics videos): If the system cannot find the corresponding model file in the directory where the command is run, it will automatically download (if download fails, you can copy the model in yourself)

Enter the project folder:

xxxxxxxxxx
cd ~/ultralytics

Use yolo26n.pt to detect the target video and output results:

Here we switched to yolo26n.engine, which is the TensorRT model we converted in the previous section. The performance on Jetson is better than yolo26n.pt

xxxxxxxxxx
yolo predict model=yolo26n.engine source='/home/jetson/ultralytics/videos/car.mp4'

Alternatively, we can directly add the show parameter to watch the video

xxxxxxxxxx
yolo predict model=yolo26n.engine source='/home/jetson/ultralytics/videos/car.mp4' show

5. Real-time Prediction

Use yolo26n.pt to predict USB camera footage: If the system cannot find the corresponding model file in the directory where the command is run, it will automatically download (if download fails, you can copy the model in yourself)

Note: CLI method does not support CSI cameras

Enter the project folder:

xxxxxxxxxx
cd ~/ultralytics

Use yolo26n.pt to detect camera footage and output results: Currently only USB cameras can directly use CLI to predict real-time footage. No relevant information found for CSI cameras as direct input sources

xxxxxxxxxx
yolo predict model=yolo26n.engine source=0 save=False show # Object detection
# Instance segmentation: yolo predict model=yolo26n-seg.pt source=0 save=False show
# Image classification: yolo predict model=yolo26n-cls.pt source=0 save=False show
# Pose estimation: yolo predict model=yolo26n-pose.pt source=0 save=False show
# Oriented object detection: yolo predict model=yolo26n-obb.pt source=0 save=False show

Click the terminal and press "Ctrl + C" shortcut to terminate the program!

Parameter Description

model: Specify YOLO model

source: Specify recognition source: multiple cameras can switch numbers

save=False: Disable saving results

show: Real-time display

Reference Materials

Home - Ultralytics YOLO Documentation

Command Line Interface - Ultralytics YOLO Documentation